Bright Data's Web MCP server enabling AI agents to search, extract & navigate the web
Nothing to run from here
ContextFetch is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
trust score
30
downloads a day
local
or remote
360
downloads in 30d
What it does
Web search and any page as LLM-ready Markdown for AI agents. Free keyless tier, no signup.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user contextfetch-mcp '--' npx -y @contextfetch/mcp
# 2 — ask your agent for something these tools do
# contextfetch_search, contextfetch_extract_url, contextfetch_find_similar and 8 more
ContextFetch costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
COAll 1 server
contextfetch1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user contextfetch-mcp '--' npx -y @contextfetch/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Or connect to its publisher’s address
Its publisher also runs it at https://api.contextfetch.dev/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http contextfetch-mcp https://api.contextfetch.dev/mcpFree on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take CONTEXTFETCH_API_KEY (ContextFetch API key. Leave unset for the free keyless tier (25 requests per day per IP).), CONTEXTFETCH_API_BASE (API base URL, only for a self-hosted engine.) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
11 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Search the web and get LLM-ready Markdown. Each result has its title, URL and only the passages relevant to the query (cross-encoder pruned context), so it costs far fewer tokens than raw pages. Use for current events, documentation, APIs, research and fact checking.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Natural-language search query. |
| num_results | integer | no | Number of results to return (1-25, default 5). |
| include_domains | array | no | Only return results from these domains, e.g. ["docs.python.org"]. |
| exclude_domains | array | no | Never return results from these domains. |
Fetch a public web page (docs, articles, GitHub files, arXiv papers) as clean Markdown with tables preserved. Pass query to get only the passages relevant to it instead of the whole page.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public http(s) URL to read. |
| query | string | no | Optional question or topic; returns only the relevant passages. |
Find pages similar to a given URL (alternatives, related docs, competing libraries), excluding the source domain. Returns titles, URLs and the most relevant passages as Markdown.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public http(s) URL to find similar pages for. |
| num_results | integer | no | Number of results to return (1-25, default 5). |
Research a question in one call, server-side: runs up to 5 web searches (sub-queries) concurrently, dedupes the pages by URL, ranks them all against the question with a cross-encoder and returns one Markdown evidence pack with numbered [n] sources and their query-pruned passages, quoted verbatim…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | The research question. |
| sub_queries | array | no | Up to 5 search queries covering different angles of the question. Recommended. |
| num_results_per_query | integer | no | Results per sub-query (1-10, default 5). |
Same as contextfetch_research (kept for existing setups): up to 3 sub-queries run server-side, sources deduped and ranked against the question, one Markdown evidence pack with numbered sources and query-pruned passages. Each sub-query is one search and costs 1 credit. You SHOULD pass your own…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | The research question. |
| sub_queries | array | no | Up to 3 search queries covering different angles of the question. Strongly recommended. |
| num_results_per_query | integer | no | Results per sub-query (1-25, default 5; at most 10 are used). |
Answer a question with passages quoted verbatim from the web, never generated: searches, scores every passage of the top pages with a cross-encoder and returns the best ones with [n] citations to their sources. Use it for quick factual lookups; the quotes may not fully answer an open-ended…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | The question. |
| num_results | integer | no | Pages searched for passages (1-10, default 5). |
Crawl one website from a start URL and get its pages as Markdown: same-site links only, up to max_depth hops (<= 3) and limit pages (<= 50), robots.txt obeyed. Pass query to rank the pages by relevance and return only their relevant passages. Costs 1 credit per page returned.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public http(s) start URL. |
| max_depth | integer | no | Link hops from the start page (0-3, default 1). |
| limit | integer | no | Maximum pages to return (1-50, default 10). |
| query | string | no | Optional topic: ranks pages and prunes each to the relevant passages. |
| include_paths | yes | — | |
| exclude_paths | yes | — |
List a website's URLs without fetching its pages: its sitemaps (from robots.txt, else /sitemap.xml) plus the start page's links, same site only, up to limit (<= 5,000). Use it to find the right pages before contextfetch_extract_url or contextfetch_crawl. Costs 1 credit.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Public http(s) URL of the site (any page on it). |
| limit | integer | no | Maximum URLs (1-5,000, default 100). |
| include_paths | yes | — | |
| exclude_paths | yes | — |
Show the API key's remaining credits, daily burn rate (7-day average) and auto-reload settings, including the last auto-reload error if a payment failed. Needs CONTEXTFETCH_API_KEY; free. Check it before long jobs.
No parameter schema on file.
Turn auto-reload on or off, or change it: when credits drop below threshold, the saved card buys pack again, up to monthly_max_usd per month. Needs CONTEXTFETCH_API_KEY and a card saved at checkout. The monthly cap cannot be raised above $500 here.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| enabled | boolean | yes | true to turn auto-reload on, false to turn it off. |
| threshold | integer | no | Reload when credits drop below this (100-100,000, default 1,000). |
| pack | string | no | Pack to buy: instant $15/15,000, builder $50/60,000, scale $150/200,000. |
| monthly_max_usd | number | no | Monthly spending cap in USD (at most 500). |
Get a free ContextFetch API key with 2,500 searches (one per network, no sign-up). This session uses it right away; give it to your user so they can set CONTEXTFETCH_API_KEY to keep it.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install ContextFetch or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 96 / 100
Release 1.0.1 · scanned 20 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 5 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digest3117c9dd241bbb6259d3b57d7ba26cd1e2cf9b5dc8bfd39f8ccf38a9fd3771fb
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (11 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| contextfetch_search | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| contextfetch_extract_url | untrusted-input | untrusted-input: keyword "fetch", declares openWorldHint: true (interacts with entities outside the server) |
| contextfetch_find_similar | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| contextfetch_research | untrusted-input | untrusted-input: keyword "web_search", declares openWorldHint: true (interacts with entities outside the server) |
| contextfetch_deep_research | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| contextfetch_answer | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| contextfetch_crawl | untrusted-input | untrusted-input: keyword "crawl", declares openWorldHint: true (interacts with entities outside the server) |
| contextfetch_map | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| contextfetch_balance | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| contextfetch_auto_reload | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| contextfetch_get_free_key | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest3117c9dd241bbb62
Scanned2026-10-20
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.0.1. Pin a release below and the command asks for exactly that one.
1.0.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish ContextFetch can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.